QW

Qwen3 Zero Coder Reasoning V2 0.8B NEO EX

QwenGGUF by DavidAUUpdated 2025-07-28
Download on Hugging Face
Parameters816M
Context40K
Layers42
Architectureqwen3
Smallest quant0.3 GB
Quick answer

Qwen3 Zero Coder Reasoning V2 0.8B NEO EX needs about 2.4 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 78 quants, from 0.3 GB (IQ2_XXS) to 1.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

Qwen3 Zero Coder Reasoning V2 0.8B NEO EX – a compact coding model with reasoning

This 0.8B parameter model is built on the Qwen3 architecture and focuses on coding and reasoning tasks. It contains 42 layers and 464 tensors, and is optimized with the NEO Imatrix dataset. The model is available in multiple GGUF quantizations for different memory budgets.

Good at

  • Coding and code generation
  • Reasoning for complex code tasks
  • Fast inference on moderate hardware

Limits

  • No vision support
  • Requires 8k context for full performance
  • License is apache-2.0

Best for

  • Drafting code snippets
  • Brainstorming programming solutions
  • Generating reasoning blocks for code

Who it’s for. Developers and researchers who need a lightweight yet capable coding model. The model is suitable for local deployment on GPUs with limited VRAM and for CPU inference when speed is acceptable.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS0.3 GB 2.2 GB
Fits Get file →
IQ2_XS0.3 GB 2.2 GB
Fits Get file →
IQ2_XXS0.3 GB 2.2 GB
Fits Get file →
IQ2_XXS0.3 GB 2.2 GB
Fits Get file →
IQ2_S0.3 GB 2.2 GB
Fits Get file →
IQ2_XS0.3 GB 2.2 GB
Fits Get file →
IQ2_XS0.3 GB 2.2 GB
Fits Get file →
Q2_K_S0.3 GB 2.2 GB
Fits Get file →
IQ2_M0.3 GB 2.2 GB
Fits Get file →
IQ2_S0.3 GB 2.2 GB
Fits Get file →
IQ2_S0.3 GB 2.2 GB
Fits Get file →
Q2_K0.3 GB 2.2 GB
Fits Get file →
IQ3_XXS0.3 GB 2.2 GB
Fits Get file →
IQ2_M0.3 GB 2.3 GB
Fits Get file →
IQ2_M0.3 GB 2.3 GB
Fits Get file →
Q2_K_S0.4 GB 2.3 GB
Fits Get file →
Q2_K_S0.4 GB 2.3 GB
Fits Get file →
IQ3_XS0.4 GB 2.3 GB
Fits Get file →
IQ3_XXS0.4 GB 2.3 GB
Fits Get file →
IQ3_XXS0.4 GB 2.3 GB
Fits Get file →
IQ3_S0.4 GB 2.3 GB
Fits Get file →
Q3_K_S0.4 GB 2.3 GB
Fits Get file →
Q2_K0.4 GB 2.3 GB
Fits Get file →
Q2_K0.4 GB 2.3 GB
Fits Get file →
IQ3_M0.4 GB 2.3 GB
Fits Get file →
IQ3_XS0.4 GB 2.3 GB
Fits Get file →
IQ3_XS0.4 GB 2.3 GB
Fits Get file →
Q3_K_M0.4 GB 2.3 GB
Fits Get file →
IQ3_S0.4 GB 2.3 GB
Fits Get file →
Q3_K_S0.4 GB 2.3 GB
Fits Get file →
IQ3_S0.4 GB 2.3 GB
Fits Get file →
Q3_K_S0.4 GB 2.3 GB
Fits Get file →
IQ3_M0.4 GB 2.3 GB
Fits Get file →
IQ3_M0.4 GB 2.3 GB
Fits Get file →
IQ4_XS0.4 GB 2.3 GB
Fits Get file →
Q3_K_L0.4 GB 2.4 GB
Fits Get file →
Q3_K_M0.5 GB 2.4 GB
Fits Get file →
Q3_K_M0.5 GB 2.4 GB
Fits Get file →
IQ4_NL0.5 GB 2.4 GB
Fits Get file →
Q4_00.5 GB 2.4 GB
Fits Get file →
Q4_K_S0.5 GB 2.4 GB
Fits Get file →
Q4_K_M0.5 GB 2.4 GB
Fits Get file →
IQ4_XS0.5 GB 2.4 GB
Fits Get file →
IQ4_XS0.5 GB 2.4 GB
Fits Get file →
Q3_K_L0.5 GB 2.4 GB
Fits Get file →
Q3_K_L0.5 GB 2.4 GB
Fits Get file →
Q4_10.5 GB 2.4 GB
Fits Get file →
IQ4_NL0.5 GB 2.4 GB
Fits Get file →
IQ4_NL0.5 GB 2.4 GB
Fits Get file →
Q4_00.5 GB 2.4 GB
Fits Get file →
Q4_00.5 GB 2.4 GB
Fits Get file →
Q4_K_S0.5 GB 2.4 GB
Fits Get file →
Q4_K_S0.5 GB 2.4 GB
Fits Get file →
Q4_K_M0.5 GB 2.4 GB
Fits Get file →
Q4_K_M0.5 GB 2.4 GB
Fits Get file →
Q5_K_S0.5 GB 2.5 GB
Fits Get file →
Q5_00.5 GB 2.5 GB
Fits Get file →
Q4_10.5 GB 2.5 GB
Fits Get file →
Q4_10.5 GB 2.5 GB
Fits Get file →
Q5_K_M0.6 GB 2.5 GB
Fits Get file →
Q5_10.6 GB 2.5 GB
Fits Get file →
Q5_K_S0.6 GB 2.5 GB
Fits Get file →
Q5_K_S0.6 GB 2.5 GB
Fits Get file →
Q5_00.6 GB 2.5 GB
Fits Get file →
Q5_00.6 GB 2.5 GB
Fits Get file →
Q5_K_M0.6 GB 2.5 GB
Fits Get file →
Q5_K_M0.6 GB 2.5 GB
Fits Get file →
Q5_10.6 GB 2.5 GB
Fits Get file →
Q5_10.6 GB 2.5 GB
Fits Get file →
Q6_K0.6 GB 2.5 GB
Fits Get file →
Q6_K0.7 GB 2.6 GB
Fits Get file →
Q6_K0.7 GB 2.6 GB
Fits Get file →
Q8_00.8 GB 2.7 GB
Fits Get file →
Q8_00.8 GB 2.7 GB
Fits Get file →
Q8_00.9 GB 2.8 GB
Fits Get file →
F161.6 GB 3.5 GB
Fits Get file →
F161.6 GB 3.5 GB
Fits Get file →
F161.6 GB 3.5 GB
Fits Get file →

For 8 GB VRAM, the IQ3_M quant (0.44 GB) is a good balance of size and performance. If more VRAM is available, Q4_K_M (0.53 GB) offers higher fidelity. For the smallest footprint, IQ2_S (0.33 GB) works well but may trade off some accuracy.

What GPU do you need for Qwen3 Zero Coder Reasoning V2 0.8B NEO EX?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is F16 (1.6 GB file, about 3.5 GB in use).

Which Qwen3 Zero Coder Reasoning V2 0.8B NEO EX quant should you choose?

Q4_K_M is the usual starting point for Qwen3 Zero Coder Reasoning V2 0.8B NEO EX: it balances file size and quality well. Here it is a 0.5 GB file.

The Q8_0 file is 0.8 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ2_XXS at 0.3 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3
Parameters816M
Layers42
Trained context40,960 tokens
KV cache (fp16)168 KB per token

Source

Quantized byDavidAU
FamilyQwen
Licenseapache-2.0
Downloads (HF)16,050
Last updated2025-07-28

Frequently asked questions about Qwen3 Zero Coder Reasoning V2 0.8B NEO EX

How much VRAM does Qwen3 Zero Coder Reasoning V2 0.8B NEO EX need?

About 2.4 GB at Q4_K_M with an 8K context window. That is the 0.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Qwen3 Zero Coder Reasoning V2 0.8B NEO EX on an 8 GB GPU?

Yes, with F16: the 1.6 GB file needs about 3.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Qwen3 Zero Coder Reasoning V2 0.8B NEO EX GGUF?

It depends on the quant: IQ2_XXS is 0.3 GB, IQ2_XS is 0.3 GB, IQ2_XXS is 0.3 GB, IQ2_XXS is 0.3 GB, IQ2_S is 0.3 GB, IQ2_XS is 0.3 GB and 72 more.

What context length does Qwen3 Zero Coder Reasoning V2 0.8B NEO EX support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download Qwen3 Zero Coder Reasoning V2 0.8B NEO EX GGUF?

The files are on Hugging Face in the DavidAU/Qwen3-Zero-Coder-Reasoning-V2-0.8B-NEO-EX-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Qwen3 Zero Coder Reasoning V2 0.8B NEO EX use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Yes, the IQ3_M quant uses about 2.3 GB of VRAM at 8k context, which fits within an 8 GB GPU.

Does the model support image inputs?

No, the model is purely text-based and does not handle vision tasks.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of Qwen3-Zero-Coder-Reasoning-V2-0.8B

Similar models

Browse all →

More from DavidAU

All by DavidAU →

More Qwen models

All Qwen →

Other tiny models

All tiny models →